| { | |
| "best_metric": 1.7148971557617188, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.07802594362625573, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015605188725251145, | |
| "grad_norm": 27.093671798706055, | |
| "learning_rate": 5e-05, | |
| "loss": 3.6352, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015605188725251145, | |
| "eval_loss": 5.159157752990723, | |
| "eval_runtime": 284.5779, | |
| "eval_samples_per_second": 15.17, | |
| "eval_steps_per_second": 1.898, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003121037745050229, | |
| "grad_norm": 35.23081970214844, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004681556617575344, | |
| "grad_norm": 47.64265823364258, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 4.2257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006242075490100458, | |
| "grad_norm": 49.69529724121094, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 4.1541, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007802594362625573, | |
| "grad_norm": 62.94880676269531, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 3.7494, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.009363113235150688, | |
| "grad_norm": 58.486602783203125, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 3.0434, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010923632107675801, | |
| "grad_norm": 47.32489776611328, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 2.4626, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012484150980200916, | |
| "grad_norm": 28.48284912109375, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.1683, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014044669852726031, | |
| "grad_norm": 36.46367645263672, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.0081, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015605188725251146, | |
| "grad_norm": 31.903751373291016, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 1.735, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01716570759777626, | |
| "grad_norm": 18.21411895751953, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 1.5997, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.018726226470301376, | |
| "grad_norm": 33.31740951538086, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 2.0939, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.02028674534282649, | |
| "grad_norm": 27.541213989257812, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 2.3984, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.021847264215351603, | |
| "grad_norm": 32.7118034362793, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.366, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.023407783087876718, | |
| "grad_norm": 28.815990447998047, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 2.2951, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.024968301960401833, | |
| "grad_norm": 22.008098602294922, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 2.1483, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.026528820832926948, | |
| "grad_norm": 19.000747680664062, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.9089, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.028089339705452063, | |
| "grad_norm": 15.313111305236816, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.7744, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.029649858577977178, | |
| "grad_norm": 12.31628131866455, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.7365, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.031210377450502293, | |
| "grad_norm": 11.852285385131836, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5183, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.032770896323027404, | |
| "grad_norm": 11.74448299407959, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.651, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03433141519555252, | |
| "grad_norm": 13.442978858947754, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.5721, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.035891934068077634, | |
| "grad_norm": 14.07254409790039, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 1.4983, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03745245294060275, | |
| "grad_norm": 16.79251480102539, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 1.4203, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.039012971813127864, | |
| "grad_norm": 23.276710510253906, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 2.2293, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.039012971813127864, | |
| "eval_loss": 1.7845427989959717, | |
| "eval_runtime": 284.5304, | |
| "eval_samples_per_second": 15.172, | |
| "eval_steps_per_second": 1.898, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.04057349068565298, | |
| "grad_norm": 11.740275382995605, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1754, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.042134009558178094, | |
| "grad_norm": 13.802135467529297, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 2.0593, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.043694528430703206, | |
| "grad_norm": 11.973353385925293, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.9128, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.045255047303228324, | |
| "grad_norm": 10.648812294006348, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.8191, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.046815566175753436, | |
| "grad_norm": 10.436445236206055, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.8078, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.048376085048278554, | |
| "grad_norm": 10.531221389770508, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.7198, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.049936603920803666, | |
| "grad_norm": 7.770738124847412, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.5549, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.051497122793328784, | |
| "grad_norm": 8.979857444763184, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.5268, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.053057641665853895, | |
| "grad_norm": 9.087567329406738, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6059, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.054618160538379014, | |
| "grad_norm": 11.504910469055176, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.345, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.056178679410904125, | |
| "grad_norm": 9.279886245727539, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 1.4742, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.05773919828342924, | |
| "grad_norm": 18.69571304321289, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 1.8889, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.059299717155954355, | |
| "grad_norm": 24.7452392578125, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.1979, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.06086023602847947, | |
| "grad_norm": 7.359485626220703, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.9981, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.062420754901004585, | |
| "grad_norm": 9.63357925415039, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 2.0834, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0639812737735297, | |
| "grad_norm": 15.735189437866211, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.824, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.06554179264605481, | |
| "grad_norm": 6.923338413238525, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.8121, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06710231151857993, | |
| "grad_norm": 11.885785102844238, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.8259, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.06866283039110505, | |
| "grad_norm": 9.307328224182129, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.661, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.07022334926363016, | |
| "grad_norm": 6.920248985290527, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.6489, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.07178386813615527, | |
| "grad_norm": 7.753159999847412, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5188, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.07334438700868039, | |
| "grad_norm": 10.333271026611328, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.4593, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.0749049058812055, | |
| "grad_norm": 9.383374214172363, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 1.4722, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07646542475373061, | |
| "grad_norm": 20.21590805053711, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 1.55, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.07802594362625573, | |
| "grad_norm": 30.963455200195312, | |
| "learning_rate": 0.0, | |
| "loss": 2.1153, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.07802594362625573, | |
| "eval_loss": 1.7148971557617188, | |
| "eval_runtime": 284.4128, | |
| "eval_samples_per_second": 15.179, | |
| "eval_steps_per_second": 1.899, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0937288838086656e+18, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |